「train」の検索結果

专为追求倍速增长的初建学校设计的教师选、育、用、留四环节体系。基于科德高中融合部真实管理经验，结合十部AI Agent架构，将人才管理从校长个人经验升级为可继承、可协同、可沉淀的组织能力。

日本語の概要は準備中です。原文の説明を表示しています。

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

日本語の概要は準備中です。原文の説明を表示しています。

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

日本語の概要は準備中です。原文の説明を表示しています。

Generate project ideas via creative constraints.

日本語の概要は準備中です。原文の説明を表示しています。

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

日本語の概要は準備中です。原文の説明を表示しています。

Reference definitions for the Agent Forge orchestration roles (lead, worker, planner, evaluator). Use when coordinating multi-agent Forge work or when you need one role's responsibilities and constraints.

日本語の概要は準備中です。原文の説明を表示しています。

Build comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools. Implements automated training, deployment, and monitoring across cloud platforms. Use PROACTIVELY for ML infrastructure, experiment management, or pipeline automation.

日本語の概要は準備中です。原文の説明を表示しています。

Detect suspicious PowerShell execution patterns including encoded commands, download cradles, AMSI bypass attempts, and constrained language mode evasion.

日本語の概要は準備中です。原文の説明を表示しています。

This skill covers deploying anomaly detection systems for industrial control environments using machine learning models trained on OT network baselines, physics-based process models, and behavioral analysis of industrial protocol communications. It addresses building normal behavior profiles for SCADA polling patterns, detecting deviations in Modbus/DNP3/OPC UA traffic, identifying rogue devices, and correlating network anomalies with physical process data from historians.

日本語の概要は準備中です。原文の説明を表示しています。

Design and execute a social engineering penetration test including phishing, vishing, smishing, and physical pretexting campaigns to measure human security resilience and identify training gaps.

日本語の概要は準備中です。原文の説明を表示しています。

Generate comprehensive documentation for content authors taking over an AEM Edge Delivery Services project. Use when onboarding content authors, training content managers, or creating author-focused handover documentation — analyzes project structure and produces a complete authoring guide with blocks, templates, configurations, and publishing workflows.

日本語の概要は準備中です。原文の説明を表示しています。

AEM Cloud Service expert skill for Sling Scheduler. Routes to path-a.md (Runnable + OSGi properties) or path-b.md (Sling Jobs via JobManager). Covers classification, CS-specific constraints (no @SlingScheduled, multi-pod runOn, Boolean type hint), review checklist, troubleshooting fingerprints, and common pitfalls.

日本語の概要は準備中です。原文の説明を表示しています。

Reference for producing Adobe Document Authoring (DA, da.live) and Edge Delivery Services (EDS, aka aem.live/Helix) compatible content. Use whenever generating HTML for DA upload, uploading media binaries to DA, publishing to aem.live, or driving the DA admin API (auth, source PUT, preview/publish). Covers block HTML format (canonical div-class form and accepted table alternate), section structure, page/section metadata, icons, links, images, default content, document skeleton constraints, block cell content normalization, the DA Source API contract, IMS auth, media storage, supported formats, Media Bus vs Content Bus delivery, and silent-failure rules that corrupt content.

日本語の概要は準備中です。原文の説明を表示しています。

Fetch up-to-date, version-specific documentation for any major library (Next.js 16, Sanity, LangGraph, React, Tailwind CSS, Vitest, Framer Motion) via the Context7 MCP server. Use when writing code against unfamiliar or recently-changed framework APIs, when training data may be stale, when resolving deprecations or version-specific syntax, or when the repo warns about framework drift (e.g. the nextjs-agent-rules block in portfolio-v1/AGENTS.md). Invokes the resolve-library-id and get-library-docs MCP tools.

日本語の概要は準備中です。原文の説明を表示しています。

Audits database schemas for naming conventions, type consistency, nullability patterns, and missing constraints. Provides violations report with recommended fixes. Use for "schema validation", "database linting", "schema standards", or "consistency checks".

日本語の概要は準備中です。原文の説明を表示しています。

Diagnoses LLM output failures including hallucinations, constraint violations, format errors, and reasoning issues. Provides root cause classification, prompt fixes, tool improvements, and new test cases. Use for "debugging AI", "fixing prompts", "quality issues", or "output errors".

日本語の概要は準備中です。原文の説明を表示しています。

Converts documents into clean, chunked datasets suitable for embeddings and vector search. Produces chunked JSONL files with metadata, deduplication logic, and quality checks. Use when preparing "training data", "vector datasets", "document processing", or "embedding data".

日本語の概要は準備中です。原文の説明を表示しています。

Implements content safety filters with PII redaction, policy constraints, prompt injection detection, and safe refusal templates. Use when adding "content moderation", "safety filters", "PII protection", or "guardrails".

日本語の概要は準備中です。原文の説明を表示しています。

Creates comprehensive developer onboarding documentation and materials including step-by-step setup guides, first-task assignments, expected time per step, common troubleshooting, team introductions, and code walkthrough tours. Use when preparing "new developer onboarding", "first day setup", "junior dev training", or "team member onboarding".

日本語の概要は準備中です。原文の説明を表示しています。

Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces.

日本語の概要は準備中です。原文の説明を表示しています。

Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.

日本語の概要は準備中です。原文の説明を表示しています。

Detects data integrity issues including orphaned records, broken foreign key relationships, constraint violations, and provides automated fix migrations. Use for "data integrity", "orphaned records", "broken relationships", or "data quality".

日本語の概要は準備中です。原文の説明を表示しています。

Use when a study's materials, data, code, or preprint need an open-science release: license choice, a persistent DOI (Zenodo/OSF), README and metadata, and an access-and-embargo decision that respects ethics constraints.

日本語の概要は準備中です。原文の説明を表示しています。

Full exploit development course roadmap and syllabus: weekly topics, recommended reading, lab setup, and learning path from vulnerability classes through advanced exploitation. Use to structure exploit dev training or onboard new researchers.

日本語の概要は準備中です。原文の説明を表示しています。